Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to directional and spatial terms related to hands and sides

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.84
     propOrder
    -0.76
     betweenstory
    -0.73
    InjectAttribute
    -0.71
    awtextra
    -0.70
    новниш
    -0.69
    ValueStyle
    -0.69
     cytok
    -0.67
     ویکی‌پدی
    -0.65
    RetentionPolicy
    -0.63
    POSITIVE LOGITS
     rhs
    0.58
    rhs
    0.57
     rü
    0.52
     lhs
    0.51
     vPvB
    0.51
     cross
    0.49
     Cross
    0.49
     left
    0.47
    Cross
    0.46
    LEAR
    0.46
    Act Density 0.015%

    No Known Activations